Feature Extraction
sentence-transformers
Safetensors
code
bert
code-search
code-retrieval
text-embeddings-inference
Instructions to use thinkingdbx/codebert-permissive-embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use thinkingdbx/codebert-permissive-embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("thinkingdbx/codebert-permissive-embed") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Stage-2 code embedding model: permissive-only corpus, function-level contrastive tuning
c3ebc49 verified | { | |
| "model": { | |
| "n_queries": 200, | |
| "n_documents": 2200, | |
| "recall": { | |
| "@1": 0.22, | |
| "@5": 0.325, | |
| "@10": 0.385 | |
| }, | |
| "mrr": 0.2679 | |
| }, | |
| "bm25": { | |
| "n_queries": 200, | |
| "n_documents": 2200, | |
| "recall": { | |
| "@1": 0.225, | |
| "@5": 0.275, | |
| "@10": 0.31 | |
| }, | |
| "mrr": 0.2546 | |
| } | |
| } |